检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhong, Lujia Huang, Shuo Shi, Yonggang Stevens Neuroimaging and Informatics Institute University of Southern California United States Ming Hsieh Department of Electrical and Computer Engineering University of Southern California United States Alfred E. Mann Department of Biomedical Engineering University of Southern California United States

Recently, deep learning has made remarkable strides, especially with generative modeling, such as large language models and probabilistic diffusion models. However, training these models often involves significant computational resources, requiring billions of petaFLOPs. This high resource consumption results in substantial energy usage and a large carbon footprint, raising critical environmental concerns. Back-propagation (BP) is a major source of computational expense during training deep learning models. To advance research on energy-efficient training and allow for sparse learning on any machine and device, we propose a general, energy-efficient convolution module that can be seamlessly integrated into any deep learning architecture. Specifically, we introduce channel-wise sparsity with additional gradient selection schedulers during backward based on the assumption that BP is often dense and inefficient, which can lead to over-fitting and high computational consumption. Our experiments demonstrate that our approach reduces 40% computations while potentially improving model performance, validated on image classification and generation tasks. This reduction can lead to significant energy savings and a lower carbon footprint during the research and development phases of large-scale AI systems. Additionally, our method mitigates over-fitting in a manner distinct from Dropout, allowing it to be combined with Dropout to further enhance model performance and reduce computational resource usage. Extensive experiments validate that our method generalizes to a variety of datasets and tasks and is compatible with a wide range of deep learning architectures and modules. Code is publicly available at https://***/lujiazho/ssProp. Copyright © 2024, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Multiple Teachers-Meticulous Student: A Domain Adaptive Meta-Knowledge Distillation Model for Medical Image Classification

arXiv

引用

arXiv 2024年

作者： Nabavi, Shahabedin Hamedani, Kian Anvari Moghaddam, Mohsen Ebrahimi Abin, Ahmad Ali Frangi, Alejandro F. Faculty of Computer Science and Engineering Shahid Beheshti University Tehran Iran Division of Informatics Imaging and Data Sciences Schools of Computer Science and Health Sciences The University of Manchester Manchester United Kingdom Electrical Engineering and Cardiovascular Sciences Departments KU Leuven Leuven Belgium Alan Turing Institute London United Kingdom

Background: Image classification can be considered one of the key pillars of medical image analysis. Deep learning (DL) faces challenges that prevent its practical applications despite the remarkable improvement in medical image classification. The data distribution differences can lead to a drop in the efficiency of DL, known as the domain shift problem. Besides, requiring bulk annotated data for model training, the large size of models, and the privacy-preserving of patients are other challenges of using DL in medical image classification. This study presents a strategy that can address the mentioned issues simultaneously. Method: The proposed domain adaptive model based on knowledge distillation can classify images by receiving limited annotated data of different distributions. The designed multiple teachers-meticulous student model trains a student network that tries to solve the challenges by receiving the parameters of several teacher networks. The proposed model was evaluated using six available datasets of different distributions by defining the respiratory motion artefact detection task. Results: The results of extensive experiments using several datasets show the superiority of the proposed model in addressing the domain shift problem and lack of access to bulk annotated data. Besides, the privacy preservation of patients by receiving only the teacher network parameters instead of the original data and consolidating the knowledge of several DL models into a model with almost similar performance are other advantages of the proposed model. Conclusions: The proposed model can pave the way for practical clinical applications of deep classification methods by achieving the mentioned objectives simultaneously. Copyright © 2024, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Statistical Distance-Guided Unsupervised Domain Adaptation for Automated Multi-Class Cardiovascular Magnetic Resonance Image Quality Assessment

arXiv

引用

arXiv 2024年

This study proposes an attention-based statistical distance-guided unsupervised domain adaptation model for multi-class cardiovascular magnetic resonance (CMR) image quality assessment. The proposed model consists of a feature extractor, a label predictor and a statistical distance estimator. An annotated dataset as the source set and an unlabeled dataset as the target set with different statistical distributions are considered inputs. The statistical distance estimator approximates the Wasserstein distance between the extracted feature vectors from the source and target data in a mini-batch. The label predictor predicts data labels of source data and uses a combinational loss function for training, which includes cross entropy and centre loss functions plus the estimated value of the distance estimator. Four datasets, including imaging and k-space data, were used to evaluate the proposed model in identifying four common CMR imaging artefacts: respiratory and cardiac motions, Gibbs ringing and Aliasing. The results of the extensive experiments showed that the proposed model, both in image and k-space analysis, has an acceptable performance in covering the domain shift between the source and target sets. The model explainability evaluations and the ablation studies confirmed the proper functioning and effectiveness of all the model's modules. The proposed model outperformed the previous studies regarding performance and the number of examined artefacts. The proposed model can be used for CMR post-imaging quality control or in large-scale cohort studies for image and k-space quality assessment due to the appropriate performance in domain shift coverage without a tedious data-labelling process. Copyright © 2024, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Fluctuation-based approaches to infer kinetics of cell-state switching

Fluctuation-based approaches to infer kinetics of cell-state...

引用

IEEE Conference on Decision and Control

作者： Michael Saint-Antoine Ramon Grima Abhyudai Singh Departments of Electrical and Computer Engineering Biomedical Engineering University of Delaware Newark DE USA School of Biological Sciences University of Edinburgh U.K.

ISBN: (数字)9781665467612

ISBN: (纸本)9781665467629

In the noisy cellular environment, RNAs and proteins are subject to considerable stochastic fluctuations in copy numbers over time. As a consequence, single cells within the same isoclonal population can differ in their expression profile and reside in different phenotypic states. Here we propose a fluctuation-test approach to infer the kinetics of transitions between cell states. More specifically, single cells are randomly drawn from the population and grown into cell colonies. After growth for a fixed number of generations, the number of cells residing in different states is assayed for each colony. In a simple system with reversible switching between two cell states, our analysis shows that the extent of colony-to-colony fluctuations in the fraction of cells in a given state is monotonically related to the switching kinetics. Several closed-form formulas for inferring the switching rates from experimentally quantified fluctuations are presented. This is especially important for scenarios where a measurement involves killing the cell (for example, performing single-cell RNA-seq or assaying whether a microbial/cancer cell is in a drug-sensitive or drug-tolerant state), and hence the state of the same cell cannot be measured at different time points.

关键词： Fluctuations RNA Sociology Stochastic processes Switches Time measurement Kinetic theory

来源：评论

学校读者我要写书评

暂无评论

Mammo-CLIP: A Vision Language Foundation Model to Enhance Data Efficiency and Robustness in Mammography

arXiv

引用

arXiv 2024年

作者： Ghosh, Shantanu Poynton, Clare B. Visweswaran, Shyam Batmanghelich, Kayhan Department of Electrical and Computer Engineering Boston University BostonMA United States Boston University Chobanian & Avedisian School of Medicine BostonMA United States Department of Biomedical Informatics University of Pittsburgh PittsburghPA United States

The lack of large and diverse training data on computer- Aided Diagnosis (CAD) in breast cancer detection has been one of the concerns that impedes the adoption of the system. Recently, pre-training with large-scale image text datasets via Vision-Language models (VLM) (e.g., CLIP) partially addresses the issue of robustness and data efficiency in computer vision (CV). This paper proposes Mammo-CLIP, the first VLM pre-trained on a substantial amount of screening mammogramreport pairs, addressing the challenges of dataset diversity and size. Our experiments on two public datasets demonstrate strong performance in classifying and localizing various mammographic attributes crucial for breast cancer detection, showcasing data efficiency and robustness similar to CLIP in CV. We also propose Mammo-FActOR, a novel feature attribution method, to provide spatial interpretation of representation with sentence-level granularity within mammography reports. Code is available publicly: https://***/batmanlab/Mammo-CLIP. © 2024, CC BY.

关键词： Mammography

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Neurological Diagnostics: Integrating 6G Technology with Deep Learning for Enhanced Detection of Multiple Sclerosis and Myelitis

Revolutionizing Neurological Diagnostics: Integrating 6G Tec...

引用

Telecommunications Conference (ITC-Egypt), International

作者： Rana M. NourEldeen Rahma A. Elshshtawy Omnia A. Elgohary Fatma Alzahraa A. Wahba Marco K. Attia Zeinab B. Abo elazm Mohamed G. Khattap Hend Galal Eldeen Mohamed Ali Hassan Mariam Mostafa Nayra Ibrahim Reem Ramadan Yomna Refaat Mennatallah Khaled Ali Maher Mohamed Abd Elaziz Ahmed Gamal Abdellatif Ibrahim Radiology and Medical Imaging Faculty of Applied Health Sciences Galala University Suez Egypt Biomedical Informatics Faculty of Computer Science and Engineering Galala University Suez Egypt Artificial Intelligence Science Program Faculty of Computer Science and Engineering Galala University Suez Egypt Department of Electronics and Electrical Communications Engineering Air Defense College Alexandria Egypt

ISBN: (数字)9798350351408

ISBN: (纸本)9798350351415

This paper proposes an alternative detection frame-work for multiple sclerosis (MS) and idiopathic acute transverse myelitis (ATM) within the 6G-enabled Internet of Medical Things (IoMT) environment. The developed framework relies on the implementation of a deep learning technique known as Dense Convolutional Networks (DenseNets) in the 6G-enabled IoMT to enhance prediction performance. To validate the performance of DenseNets, we compared it with other deep learning techniques, including Convolutional Neural Networks (CNN) and MobileNet, using real-world datasets. The experimental results show the high performance of DenseNets in predicting MS and ATM compared to other methods, achieving an accuracy of nearly 90 %.

关键词： 6G mobile communication Deep learning Multiple sclerosis Accuracy Internet of Medical Things Telecommunications Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Acute Ischemic Stroke Diagnosis Using IoMT and Deep Learning Technologies

Enhancing Acute Ischemic Stroke Diagnosis Using IoMT and Dee...

引用

Telecommunications Conference (ITC-Egypt), International

作者： Mohamed M. El-Sheikh Aya Bayoumy Nada M. Ahmed Amany Mohamed Eldeeb Fatma I. Rabea Amira A. Nawar Mohamed G. Khattap Hend Galal Eldeen Mohamed Ali Hassan Mariam Mostafa Nayra Ibrahim Reem Ramadan Yomna Refaat Mennatallah Khaled Ali Maher Mohamed Abd Elaziz Ahmed Gamal Abdellatif Ibrahim Radiology and Medical Imaging Faculty of Applied Health Sciences Galala University Suez Egypt Biomedical Informatics Faculty of Computer Science and Engineering Galala University Suez Egypt Artificial Intelligence Science Program Faculty of Computer Science and Engineering Galala University Suez Egypt Department of Electronics and Electrical Communications Engineering Air Defense College Alexandria Egypt

ISBN: (数字)9798350351408

ISBN: (纸本)9798350351415

This paper introduces an alternative technique for diagnosing Acute Ischemic Stroke within the IoMT environment. In the proposed approach, the collected data is transmitted to a cloud-based center where the technique utilizes EfficientNet, a deep learning model, designed to extract features from MRI images thereby enhancing the detection of acute ischemic infarctions. The performance of EfficientNet is compared against two other models, CNN and MobileNet, demonstrating its superior efficacy through metrics such as accuracy, precision, recall, and F1-score, which stand at 92.31%, 92.28%, 92.33%, and 92.30%, respectively.

关键词： Deep learning Accuracy Magnetic resonance imaging Soft sensors Medical services Feature extraction Regulation

来源：评论

学校读者我要写书评

暂无评论

CincyMedIR at TREC 2021 Clinical Trial Track 30

CincyMedIR at TREC 2021 Clinical Trial Track

引用

30th Text REtrieval Conference, TREC 2021

作者： Vu, Hoang Wu, Danny T.Y. Department of Biomedical Informatics University of Cincinnati College of Medicine CincinnatiOH United States Department of Electrical Engineering and Computer Science College of Engineering and Applied Science University of Cincinnati CincinnatiOH United States

来源：评论

学校读者我要写书评

暂无评论

Fundamentals of Machine Learning and Deep Learning in Medicine 1

引用

2022年

作者： Reza Borhani Aggelos K. Katsaggelos Soheila Borhani

ISBN: (数字)9783031195020

ISBN: (纸本)9783031195013

This book provides an accessible introduction to the foundations of machine learning and deep learning in medicine for medical students, researchers, and professionals who are not necessarily initiated in advanced mathematics but yearn for a better understanding of this disruptive technology and its impact on medicine. Once an esoteric subject known to few outside of computer science and engineering departments, today artificial intelligence (AI) is a widely popular technology used by scholars from all across the academic universe. In particular, recent years have seen a great deal of interest in the AI subfields of machine learning and deep learning from researchers in medicine and life sciences, evidenced by the rapid growth in the number of articles published on the topic in peer-reviewed medical journals over the last decade. The demand for high-quality educational resources in this area has never been greater than it is today, and will only continue to grow at a rapid *** authors remove the veil of unnecessary complexity that often surrounds machine learning and deep learning by employing a narrative style that emphasizes intuition in place of abstract mathematical formalisms, allowing them to strike a delicate balance between practicality and theoretical rigor in service of facilitating the reader’s learning experience. Topics covered in the book include: mathematical encoding of medical data, linear regression and classification, nonlinear feature engineering, deep learning, convolutional and recurrent neural networks, and reinforcement learning. Each chapter ends with a collection of exercises for readers to practice and test their *** is an ideal introduction for medical students, professionals, and researchers interested in learning more about machine learning and deep learning. Readers who have taken at least one introductory mathematics course at the undergraduate-level (e.g., biostatistics or calculus) will be well-equipped to use thi

关键词： Internal Medicine Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Large-Scale Electron Microscopy to Find Nanoscale Detail in Cancer

引用

Microscopy and microanalysis : the official journal of Microscopy Society of America, Microbeam Analysis Society, Microscopical Society of Canada 2023年第1期29卷 1078-1079页

作者： Riesterer, Jessica L. Bueno, Cecilia Stempinski, Erin S. Adamou, Steven K. López, Claudia S. Thibault, Guillaume Pagano, Lucas Grieco, Joseph Olson, Samuel Machireddy, Archana Chang, Young Hwan Song, Xubo Gray, Joe W. Knight Cancer Institute Oregon Health & Science University Portland OR USA Multiscale Microscopy Core Oregon Health & Science University Portland OR USA Pacific Northwest Center for Cryo-EM Oregon Health & Science University Portland OR USA Department of Biomedical Engineering Oregon Health & Science University Portland OR USA Department of Medical Informatics & Clinical Epidemiology at Oregon Health & Science University Portland OR USA Computer Science &Electrical Engineering Oregon Health & Science University Portland OR USA

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：